1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
|
/*
FUNCTION
<<setlocale>>, <<localeconv>>---select or query locale
INDEX
setlocale
INDEX
localeconv
INDEX
_setlocale_r
INDEX
_localeconv_r
ANSI_SYNOPSIS
#include <locale.h>
char *setlocale(int <[category]>, const char *<[locale]>);
lconv *localeconv(void);
char *_setlocale_r(void *<[reent]>,
int <[category]>, const char *<[locale]>);
lconv *_localeconv_r(void *<[reent]>);
TRAD_SYNOPSIS
#include <locale.h>
char *setlocale(<[category]>, <[locale]>)
int <[category]>;
char *<[locale]>;
lconv *localeconv();
char *_setlocale_r(<[reent]>, <[category]>, <[locale]>)
char *<[reent]>;
int <[category]>;
char *<[locale]>;
lconv *_localeconv_r(<[reent]>);
char *<[reent]>;
DESCRIPTION
<<setlocale>> is the facility defined by ANSI C to condition the
execution environment for international collating and formatting
information; <<localeconv>> reports on the settings of the current
locale.
This is a minimal implementation, supporting only the required <<"POSIX">>
and <<"C">> values for <[locale]>; strings representing other locales are not
honored unless _MB_CAPABLE is defined.
If _MB_CAPABLE is defined, POSIX locale strings are allowed, following
the form
language[_TERRITORY][.charset][@@modifier]
<<"language">> is a two character string per ISO 639, or, if not available
for a given language, a three character string per ISO 639-3.
<<"TERRITORY">> is a country code per ISO 3166. For <<"charset">> and
<<"modifier">> see below.
Additionally to the POSIX specifier, the following extension is supported
for backward compatibility with older implementations using newlib:
<<"C-charset">>.
Instead of <<"C-">>, you can also specify <<"C.">>. Both variations allow
to specify language neutral locales while using other charsets than ASCII,
for instance <<"C.UTF-8">>, which keeps all settings as in the C locale,
but uses the UTF-8 charset.
The following charsets are recogized:
<<"UTF-8">>, <<"JIS">>, <<"EUCJP">>, <<"SJIS">>, <<"KOI8-R">>, <<"KOI8-U">>,
<<"GEORGIAN-PS">>, <<"PT154">>, <<"TIS-620">>, <<"ISO-8859-x">> with
1 <= x <= 16, or <<"CPxxx">> with xxx in [437, 720, 737, 775, 850, 852, 855,
857, 858, 862, 866, 874, 932, 1125, 1250, 1251, 1252, 1253, 1254, 1255, 1256,
1257, 1258].
Charsets are case insensitive. For instance, <<"EUCJP">> and <<"eucJP">>
are equivalent. Charset names with dashes can also be written without
dashes, as in <<"UTF8">>, <<"iso88591">> or <<"koi8r">>. <<"EUCJP">> and
<<"EUCKR"> are also recognized with dash, <<"EUC-JP">> and <<"EUC-KR">>.
Full support for all of the above charsets requires that newlib has been
build with multibyte support and support for all ISO and Windows Codepage.
Otherwise all singlebyte charsets are simply mapped to ASCII. Right now,
only newlib for Cygwin is built with full charset support by default.
Under Cygwin, this implementation additionally supports the charsets
<<"GBK">>, <<"eucKR">>, and <<"Big5">>. Cygwin does not support <<"JIS">>.
(<<"">> is also accepted; if given, the settings are read from the
corresponding LC_* environment variables and $LANG according to POSIX rules.
This implementation also supports a single modifier, <<"cjknarrow">>.
Any other modifier is ignored. <<"cjknarrow">>, in conjunction with one
of the language specifiers <<"ja">>, <<"ko">>, and <<"zh">> specifies
how the functions <<wcwidth>> and <<wcswidth>> handle characters from
the "CJK Ambiguous Width" character class described in
http://www.unicode.org/unicode/reports/tr11/. Usually these characters
have a width of 1, unless you specify one of the aforementioned
languages, in which case these characters have a width of 2. By
specifying the <<"cjknarrow">> modifier, these characters will have a
width of one in the languages <<"ja">>, <<"ko">>, and <<"zh">> as well.
If you use <<NULL>> as the <[locale]> argument, <<setlocale>> returns a
pointer to the string representing the current locale. The acceptable
values for <[category]> are defined in `<<locale.h>>' as macros
beginning with <<"LC_">>.
<<localeconv>> returns a pointer to a structure (also defined in
`<<locale.h>>') describing the locale-specific conventions currently
in effect.
<<_localeconv_r>> and <<_setlocale_r>> are reentrant versions of
<<localeconv>> and <<setlocale>> respectively. The extra argument
<[reent]> is a pointer to a reentrancy structure.
RETURNS
A successful call to <<setlocale>> returns a pointer to a string
associated with the specified category for the new locale. The string
returned by <<setlocale>> is such that a subsequent call using that
string will restore that category (or all categories in case of LC_ALL),
to that state. The application shall not modify the string returned
which may be overwritten by a subsequent call to <<setlocale>>.
On error, <<setlocale>> returns <<NULL>>.
<<localeconv>> returns a pointer to a structure of type <<lconv>>,
which describes the formatting and collating conventions in effect (in
this implementation, always those of the C locale).
PORTABILITY
ANSI C requires <<setlocale>>, but the only locale required across all
implementations is the C locale.
NOTES
There is no ISO-8859-12 codepage. It's also refused by this implementation.
No supporting OS subroutines are required.
*/
/* Parts of this code are originally taken from FreeBSD. */
/*
* Copyright (c) 1996 - 2002 FreeBSD Project
* Copyright (c) 1991, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Paul Borman at Krystal Technologies.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <newlib.h>
#include <errno.h>
#include <locale.h>
#include <string.h>
#include <limits.h>
#include <reent.h>
#include <stdlib.h>
#include <wchar.h>
#include "lmonetary.h"
#include "lnumeric.h"
#include "../stdlib/local.h"
#define _LC_LAST 7
#define ENCODING_LEN 31
int __EXPORT __mb_cur_max = 1;
int __nlocale_changed = 0;
int __mlocale_changed = 0;
char *_PathLocale = NULL;
static
#ifndef __CYGWIN__
_CONST
#endif /* !__CYGWIN__ */
struct lconv lconv =
{
".", "", "", "", "", "", "", "", "", "",
CHAR_MAX, CHAR_MAX, CHAR_MAX, CHAR_MAX,
CHAR_MAX, CHAR_MAX, CHAR_MAX, CHAR_MAX,
CHAR_MAX, CHAR_MAX, CHAR_MAX, CHAR_MAX,
CHAR_MAX, CHAR_MAX
};
#ifdef _MB_CAPABLE
/*
* Category names for getenv()
*/
static char *categories[_LC_LAST] = {
"LC_ALL",
"LC_COLLATE",
"LC_CTYPE",
"LC_MONETARY",
"LC_NUMERIC",
"LC_TIME",
"LC_MESSAGES",
};
/*
* Default locale per POSIX. Can be overridden on a per-target base.
*/
#ifndef DEFAULT_LOCALE
#define DEFAULT_LOCALE "C"
#endif
/*
* This variable can be changed by any outside mechanism. This allows,
* for instance, to load the default locale from a file.
*/
char __default_locale[ENCODING_LEN + 1] = DEFAULT_LOCALE;
/*
* Current locales for each category
*/
static char current_categories[_LC_LAST][ENCODING_LEN + 1] = {
"C",
"C",
"C",
"C",
"C",
"C",
"C",
};
/*
* The locales we are going to try and load
*/
static char new_categories[_LC_LAST][ENCODING_LEN + 1];
static char saved_categories[_LC_LAST][ENCODING_LEN + 1];
static char current_locale_string[_LC_LAST * (ENCODING_LEN + 1/*"/"*/ + 1)];
static char *currentlocale(void);
static char *loadlocale(struct _reent *, int);
static const char *__get_locale_env(struct _reent *, int);
#endif
#if 0 /*def __CYGWIN__ TODO: temporarily(?) disable C == UTF-8 */
static char lc_ctype_charset[ENCODING_LEN + 1] = "UTF-8";
static char lc_message_charset[ENCODING_LEN + 1] = "UTF-8";
#else
static char lc_ctype_charset[ENCODING_LEN + 1] = "ASCII";
static char lc_message_charset[ENCODING_LEN + 1] = "ASCII";
#endif
static int lc_ctype_cjk_lang = 0;
char *
_DEFUN(_setlocale_r, (p, category, locale),
struct _reent *p _AND
int category _AND
_CONST char *locale)
{
#ifndef _MB_CAPABLE
if (locale)
{
if (strcmp (locale, "POSIX") && strcmp (locale, "C")
&& strcmp (locale, ""))
return NULL;
}
return "C";
#else
int i, j, len, saverr;
const char *env, *r;
if (category < LC_ALL || category >= _LC_LAST)
{
p->_errno = EINVAL;
return NULL;
}
if (locale == NULL)
return category != LC_ALL ? current_categories[category] : currentlocale();
/*
* Default to the current locale for everything.
*/
for (i = 1; i < _LC_LAST; ++i)
strcpy (new_categories[i], current_categories[i]);
/*
* Now go fill up new_categories from the locale argument
*/
if (!*locale)
{
if (category == LC_ALL)
{
for (i = 1; i < _LC_LAST; ++i)
{
env = __get_locale_env (p, i);
if (strlen (env) > ENCODING_LEN)
{
p->_errno = EINVAL;
return NULL;
}
strcpy (new_categories[i], env);
}
}
else
{
env = __get_locale_env (p, category);
if (strlen (env) > ENCODING_LEN)
{
p->_errno = EINVAL;
return NULL;
}
strcpy (new_categories[category], env);
}
}
else if (category != LC_ALL)
{
if (strlen (locale) > ENCODING_LEN)
{
p->_errno = EINVAL;
return NULL;
}
strcpy (new_categories[category], locale);
}
else
{
if ((r = strchr (locale, '/')) == NULL)
{
if (strlen (locale) > ENCODING_LEN)
{
p->_errno = EINVAL;
return NULL;
}
for (i = 1; i < _LC_LAST; ++i)
strcpy (new_categories[i], locale);
}
else
{
for (i = 1; r[1] == '/'; ++r)
;
if (!r[1])
{
p->_errno = EINVAL;
return NULL; /* Hmm, just slashes... */
}
do
{
if (i == _LC_LAST)
break; /* Too many slashes... */
if ((len = r - locale) > ENCODING_LEN)
{
p->_errno = EINVAL;
return NULL;
}
strlcpy (new_categories[i], locale, len + 1);
i++;
while (*r == '/')
r++;
locale = r;
while (*r && *r != '/')
r++;
}
while (*locale);
while (i < _LC_LAST)
{
strcpy (new_categories[i], new_categories[i-1]);
i++;
}
}
}
if (category != LC_ALL)
return loadlocale (p, category);
for (i = 1; i < _LC_LAST; ++i)
{
strcpy (saved_categories[i], current_categories[i]);
if (loadlocale (p, i) == NULL)
{
saverr = p->_errno;
for (j = 1; j < i; j++)
{
strcpy (new_categories[j], saved_categories[j]);
if (loadlocale (p, j) == NULL)
{
strcpy (new_categories[j], "C");
loadlocale (p, j);
}
}
p->_errno = saverr;
return NULL;
}
}
return currentlocale ();
#endif
}
#ifdef _MB_CAPABLE
static char *
currentlocale()
{
int i;
(void)strcpy(current_locale_string, current_categories[1]);
for (i = 2; i < _LC_LAST; ++i)
if (strcmp(current_categories[1], current_categories[i])) {
for (i = 2; i < _LC_LAST; ++i) {
(void)strcat(current_locale_string, "/");
(void)strcat(current_locale_string,
current_categories[i]);
}
break;
}
return (current_locale_string);
}
#endif
#ifdef _MB_CAPABLE
#ifdef __CYGWIN__
extern void __set_charset_from_locale (const char *locale, char *charset);
extern int __collate_load_locale (const char *, void *, const char *);
#endif /* __CYGWIN__ */
extern void __set_ctype (const char *charset);
static char *
loadlocale(struct _reent *p, int category)
{
/* At this point a full-featured system would just load the locale
specific data from the locale files.
What we do here for now is to check the incoming string for correctness.
The string must be in one of the allowed locale strings, either
one in POSIX-style, or one in the old newlib style to maintain
backward compatibility. If the local string is correct, the charset
is extracted and stored in lc_ctype_charset or lc_message_charset
dependent on the cateogry. */
char *locale = new_categories[category];
char charset[ENCODING_LEN + 1];
unsigned long val;
char *end, *c;
int mbc_max;
int (*l_wctomb) (struct _reent *, char *, wchar_t, const char *, mbstate_t *);
int (*l_mbtowc) (struct _reent *, wchar_t *, const char *, size_t,
const char *, mbstate_t *);
#ifdef _MB_CAPABLE
int cjknarrow = 0;
#endif
#ifdef __CYGWIN__
int ret = 0;
#endif
/* "POSIX" is translated to "C", as on Linux. */
if (!strcmp (locale, "POSIX"))
strcpy (locale, "C");
if (!strcmp (locale, "C")) /* Default "C" locale */
#if 0 /*def __CYGWIN__ TODO: temporarily(?) disable C == UTF-8 */
strcpy (charset, "UTF-8");
#else
strcpy (charset, "ASCII");
#endif
else if (locale[0] == 'C'
&& (locale[1] == '-' /* Old newlib style */
|| locale[1] == '.')) /* Extension for the C locale to allow
specifying different charsets while
sticking to the C locale in terms
of sort order, etc. Proposed in
the Debian project. */
strcpy (charset, locale + 2);
else /* POSIX style */
{
c = locale;
/* Don't use ctype macros here, they might be localized. */
/* Language */
if (c[0] < 'a' || c[0] > 'z'
|| c[1] < 'a' || c[1] > 'z')
return NULL;
c += 2;
/* Allow three character Language per ISO 639-3 */
if (c[0] >= 'a' && c[0] <= 'z')
++c;
if (c[0] == '_')
{
/* Territory */
++c;
if (c[0] < 'A' || c[0] > 'Z'
|| c[1] < 'A' || c[1] > 'Z')
return NULL;
c += 2;
}
if (c[0] == '.')
{
/* Charset */
char *chp;
++c;
strcpy (charset, c);
if ((chp = strchr (charset, '@')))
/* Strip off modifier */
*chp = '\0';
c += strlen (charset);
}
else if (c[0] == '\0' || c[0] == '@')
/* End of string or just a modifier */
#ifdef __CYGWIN__
__set_charset_from_locale (locale, charset);
#else
strcpy (charset, "ISO-8859-1");
#endif
else
/* Invalid string */
return NULL;
#ifdef _MB_CAPABLE
if (c[0] == '@')
{
/* Modifier */
/* Only one modifier is recognized right now. "cjknarrow" is used
to modify the behaviour of wcwidth() for East Asian languages.
For details see the comment at the end of this function. */
if (!strcmp (c + 1, "cjknarrow"))
cjknarrow = 1;
}
#endif
}
/* We only support this subset of charsets. */
switch (charset[0])
{
case 'U':
case 'u':
if (strcasecmp (charset, "UTF-8") && strcasecmp (charset, "UTF8"))
return NULL;
strcpy (charset, "UTF-8");
mbc_max = 6;
#ifdef _MB_CAPABLE
l_wctomb = __utf8_wctomb;
l_mbtowc = __utf8_mbtowc;
#endif
break;
#ifndef __CYGWIN__
case 'J':
case 'j':
if (strcasecmp (charset, "JIS"))
return NULL;
strcpy (charset, "JIS");
mbc_max = 8;
#ifdef _MB_CAPABLE
l_wctomb = __jis_wctomb;
l_mbtowc = __jis_mbtowc;
#endif
break;
#endif /* !__CYGWIN__ */
case 'E':
case 'e':
if (!strcasecmp (charset, "EUCJP") || !strcasecmp (charset, "EUC-JP"))
{
strcpy (charset, "EUCJP");
mbc_max = 3;
#ifdef _MB_CAPABLE
l_wctomb = __eucjp_wctomb;
l_mbtowc = __eucjp_mbtowc;
#endif
}
#ifdef __CYGWIN__
else if (!strcasecmp (charset, "EUCKR")
|| !strcasecmp (charset, "EUC-KR"))
{
strcpy (charset, "EUCKR");
mbc_max = 2;
#ifdef _MB_CAPABLE
l_wctomb = __kr_wctomb;
l_mbtowc = __kr_mbtowc;
#endif
}
#endif /* __CYGWIN__ */
else
return NULL;
break;
case 'S':
case 's':
if (strcasecmp (charset, "SJIS"))
return NULL;
strcpy (charset, "SJIS");
mbc_max = 2;
#ifdef _MB_CAPABLE
l_wctomb = __sjis_wctomb;
l_mbtowc = __sjis_mbtowc;
#endif
break;
case 'I':
case 'i':
/* Must be exactly one of ISO-8859-1, [...] ISO-8859-16, except for
ISO-8859-12. This code also recognizes the aliases without dashes. */
if (strncasecmp (charset, "ISO", 3))
return NULL;
c = charset + 3;
if (*c == '-')
++c;
if (strncasecmp (c, "8859", 4))
return NULL;
c += 4;
if (*c == '-')
++c;
val = _strtol_r (p, c, &end, 10);
if (val < 1 || val > 16 || val == 12 || *end)
return NULL;
strcpy (charset, "ISO-8859-");
c = charset + 9;
if (val > 10)
*c++ = '1';
*c++ = val % 10 + '0';
*c = '\0';
mbc_max = 1;
#ifdef _MB_CAPABLE
#ifdef _MB_EXTENDED_CHARSETS_ISO
l_wctomb = __iso_wctomb;
l_mbtowc = __iso_mbtowc;
#else /* !_MB_EXTENDED_CHARSETS_ISO */
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif /* _MB_EXTENDED_CHARSETS_ISO */
#endif
break;
case 'C':
case 'c':
if (charset[1] != 'P' && charset[1] != 'p')
return NULL;
strncpy (charset, "CP", 2);
val = _strtol_r (p, charset + 2, &end, 10);
if (*end)
return NULL;
switch (val)
{
case 437:
case 720:
case 737:
case 775:
case 850:
case 852:
case 855:
case 857:
case 858:
case 862:
case 866:
case 874:
case 1125:
case 1250:
case 1251:
case 1252:
case 1253:
case 1254:
case 1255:
case 1256:
case 1257:
case 1258:
mbc_max = 1;
#ifdef _MB_CAPABLE
#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
l_wctomb = __cp_wctomb;
l_mbtowc = __cp_mbtowc;
#else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
#endif
break;
case 932:
mbc_max = 2;
#ifdef _MB_CAPABLE
l_wctomb = __sjis_wctomb;
l_mbtowc = __sjis_mbtowc;
#endif
break;
default:
return NULL;
}
break;
case 'K':
case 'k':
/* KOI8-R, KOI8-U and the aliases without dash */
if (strncasecmp (charset, "KOI8", 4))
return NULL;
c = charset + 4;
if (*c == '-')
++c;
if (*c == 'R' || *c == 'r')
strcpy (charset, "CP20866");
else if (*c == 'U' || *c == 'u')
strcpy (charset, "CP21866");
else
return NULL;
mbc_max = 1;
#ifdef _MB_CAPABLE
#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
l_wctomb = __cp_wctomb;
l_mbtowc = __cp_mbtowc;
#else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
#endif
break;
case 'A':
case 'a':
if (strcasecmp (charset, "ASCII"))
return NULL;
strcpy (charset, "ASCII");
mbc_max = 1;
#ifdef _MB_CAPABLE
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif
break;
case 'G':
case 'g':
#ifdef __CYGWIN__
if (!strcasecmp (charset, "GBK"))
{
strcpy (charset, "GBK");
mbc_max = 2;
#ifdef _MB_CAPABLE
l_wctomb = __gbk_wctomb;
l_mbtowc = __gbk_mbtowc;
#endif
}
else
#endif /* __CYGWIN__ */
/* GEORGIAN-PS and the alias without dash */
if (!strncasecmp (charset, "GEORGIAN", 8))
{
c = charset + 8;
if (*c == '-')
++c;
if (strcasecmp (c, "PS"))
return NULL;
strcpy (charset, "CP101");
mbc_max = 1;
#ifdef _MB_CAPABLE
#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
l_wctomb = __cp_wctomb;
l_mbtowc = __cp_mbtowc;
#else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
#endif
}
else
return NULL;
break;
case 'P':
case 'p':
/* PT154 */
if (strcasecmp (charset, "PT154"))
return NULL;
strcpy (charset, "CP102");
mbc_max = 1;
#ifdef _MB_CAPABLE
#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
l_wctomb = __cp_wctomb;
l_mbtowc = __cp_mbtowc;
#else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
#endif
break;
case 'T':
case 't':
if (strncasecmp (charset, "TIS", 3))
return NULL;
c = charset + 3;
if (*c == '-')
++c;
if (strcasecmp (c, "620"))
return NULL;
strcpy (charset, "CP874");
mbc_max = 1;
#ifdef _MB_CAPABLE
#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
l_wctomb = __cp_wctomb;
l_mbtowc = __cp_mbtowc;
#else /* !_MB_EXTENDED_CHARSETS_WINDOWS */
l_wctomb = __ascii_wctomb;
l_mbtowc = __ascii_mbtowc;
#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
#endif
break;
#ifdef __CYGWIN__
case 'B':
case 'b':
if (strcasecmp (charset, "BIG5"))
return NULL;
strcpy (charset, "BIG5");
mbc_max = 2;
#ifdef _MB_CAPABLE
l_wctomb = __big5_wctomb;
l_mbtowc = __big5_mbtowc;
#endif
break;
#endif /* __CYGWIN__ */
default:
return NULL;
}
if (category == LC_CTYPE)
{
strcpy (lc_ctype_charset, charset);
__mb_cur_max = mbc_max;
#ifdef _MB_CAPABLE
__wctomb = l_wctomb;
__mbtowc = l_mbtowc;
__set_ctype (charset);
/* Check for the language part of the locale specifier. In case
of "ja", "ko", or "zh", assume the use of CJK fonts, unless the
"@cjknarrow" modifier has been specifed.
The result is stored in lc_ctype_cjk_lang and tested in wcwidth()
to figure out the width to return (1 or 2) for the "CJK Ambiguous
Width" category of characters. */
lc_ctype_cjk_lang = !cjknarrow
&& ((strncmp (locale, "ja", 2) == 0
|| strncmp (locale, "ko", 2) == 0
|| strncmp (locale, "zh", 2) == 0));
#endif
}
else if (category == LC_MESSAGES)
strcpy (lc_message_charset, charset);
#ifdef __CYGWIN__
else if (category == LC_COLLATE)
ret = __collate_load_locale (locale, (void *) l_mbtowc, charset);
else if (category == LC_MONETARY)
ret = __monetary_load_locale (locale, (void *) l_wctomb, charset);
else if (category == LC_NUMERIC)
ret = __numeric_load_locale (locale, (void *) l_wctomb, charset);
else if (category == LC_TIME)
ret = __time_load_locale (locale, (void *) l_wctomb, charset);
if (ret)
return NULL;
#endif /* __CYGWIN__ */
return strcpy(current_categories[category], new_categories[category]);
}
static const char *
__get_locale_env(struct _reent *p, int category)
{
const char *env;
/* 1. check LC_ALL. */
env = _getenv_r (p, categories[0]);
/* 2. check LC_* */
if (env == NULL || !*env)
env = _getenv_r (p, categories[category]);
/* 3. check LANG */
if (env == NULL || !*env)
env = _getenv_r (p, "LANG");
/* 4. if none is set, fall to default locale */
if (env == NULL || !*env)
env = __default_locale;
return env;
}
#endif
char *
_DEFUN_VOID(__locale_charset)
{
return lc_ctype_charset;
}
char *
_DEFUN_VOID(__locale_msgcharset)
{
return lc_message_charset;
}
int
_DEFUN_VOID(__locale_cjk_lang)
{
return lc_ctype_cjk_lang;
}
struct lconv *
_DEFUN(_localeconv_r, (data),
struct _reent *data)
{
#ifdef __CYGWIN__
if (__nlocale_changed)
{
struct lc_numeric_T *n = __get_current_numeric_locale ();
lconv.decimal_point = n->decimal_point;
lconv.thousands_sep = n->thousands_sep;
lconv.grouping = n->grouping;
__nlocale_changed = 0;
}
if (__mlocale_changed)
{
struct lc_monetary_T *m = __get_current_monetary_locale ();
lconv.int_curr_symbol = m->int_curr_symbol;
lconv.currency_symbol = m->currency_symbol;
lconv.mon_decimal_point = m->mon_decimal_point;
lconv.mon_thousands_sep = m->mon_thousands_sep;
lconv.mon_grouping = m->mon_grouping;
lconv.positive_sign = m->positive_sign;
lconv.negative_sign = m->negative_sign;
lconv.int_frac_digits = m->int_frac_digits[0];
lconv.frac_digits = m->frac_digits[0];
lconv.p_cs_precedes = m->p_cs_precedes[0];
lconv.p_sep_by_space = m->p_sep_by_space[0];
lconv.n_cs_precedes = m->n_cs_precedes[0];
lconv.n_sep_by_space = m->n_sep_by_space[0];
lconv.p_sign_posn = m->p_sign_posn[0];
lconv.n_sign_posn = m->n_sign_posn[0];
lconv.int_n_cs_precedes = m->n_cs_precedes[0];
lconv.int_n_sep_by_space = m->n_sep_by_space[0];
lconv.int_n_sign_posn = m->n_sign_posn[0];
lconv.int_p_cs_precedes = m->p_cs_precedes[0];
lconv.int_p_sep_by_space = m->p_sep_by_space[0];
lconv.int_p_sign_posn = m->p_sign_posn[0];
__mlocale_changed = 0;
}
#endif /* __CYGWIN__ */
return (struct lconv *) &lconv;
}
#ifndef _REENT_ONLY
#ifndef __CYGWIN__
char *
_DEFUN(setlocale, (category, locale),
int category _AND
_CONST char *locale)
{
return _setlocale_r (_REENT, category, locale);
}
#endif /* __CYGWIN__ */
struct lconv *
_DEFUN_VOID(localeconv)
{
return _localeconv_r (_REENT);
}
#endif
|